Anomaly detection is suitable for active sonar classification due to its ability to handle the challenges posed by small imbalanced data sets. Recently, a modified anomaly detection approach called bisphere anomaly detection (BiSAD) has been developed for active sonar classification and has demonstrated improved generalization performance over conventional deep-learning-based methods. However, BiSAD has some limitations: multimodalities of clutter distribution induce unnecessary redundancy in the clutter manifold, and the inconsistency of two encoder outputs causes instability during learning. We propose a modified version of BiSAD called multisphere anomaly detection (MulSAD), which incorporates clustering and regularization. Clustering is used to model the multimodal distribution of the clutter samples, whereas regularization ensures consistency in the manifold learning of the two encoders. Two active sonar data sets generated in two different ocean experiments with different environments are used alternatively as the training/validation and test data sets. The efficacy of the modifications is confirmed by analyzing the classification performance according to hyperparameters. In the generalization test, MulSAD outperforms both the supervised-learning-based deep learning methods and BiSAD. Furthermore, MulSAD is more robust to mislabeled data samples in the training data sets.

In this study, we propose a reverberation suppression algorithm for linear frequency-modulated (LFM) pulse sonar systems using a non-negative matrix factorization (NMF) method. Because conventional NMF-based reverberation suppression algorithms are only applicable to continuous wave reverberation, we propose two pre-processing methods, namely dechirping transformation and modulo operation, to facilitate application of the NMF method to LFM reverberation. Moreover, we impose additional sparse constraints on the NMF method to improve its performance. To evaluate the proposed algorithm, an experiment involving simulated LFM reverberation is performed. The results thereof show improved detection performance at several signal-to-reverberation ratios and false alarm conditions. Moreover, the proposed algorithm is also applied to sea experiment data. According to the sea experiment analysis, the algorithm is able to suppress the LFM reverberation effectively and improve detection performance in practical LFM pulse sonar systems.

For decades, the soft-kill strategy which detects high-speed underwater targets with passive sonar and attract the targets using decoys has been used. However, recently, the paradigm to respond to the high-speed underwater targets is shifting to a hard-kill method that directly intercepts the targets. Therefore, an active sonar detection and tracking technique is required to estimate the exact location of the target. Existing detection and tracking techniques using active sonar divide pulses either temporally or along the frequency axis, transmitting pulses in various directions within a pulse repetition interval. This division, however, leads to a reduction in the time-bandwidth product, consequently diminishing detection performance. Therefore, this paper proposes a generalized sinusoidal frequency modulation (GSFM)-based pulsed active sonar (PAS). The proposed PAS-GSFM employs short pulses for a quick update of target estimates, but the orthogonality between pulses of GSFM allows pulses to maximize bandwidth, thus high detection performance can be expected. Two types of simulations were performed to verify the performance of the proposed PAS-GSFM. First, the performance comparison with PAS-linear frequency modulation (LFM), and second, the comparison between the proposed method and continuous active sonar (CAS)-GSFM. Through the evaluation, the superiority of the proposed method over PAS-LFM and competitiveness compared to CAS-GSFM were proved.

Machine learning (ML)-based approaches are desirable for discriminating targets from clutter signals to enhance the performance of active sonar systems. However, a small dataset and imbalanced data samples between the target and clutter hinder ML applications in active sonar classification. Anomaly detection (AD), which effectively exploits the imbalance, is adopted to enhance the generalization of ML-based active sonar classifiers for small and imbalanced datasets. Generally, deep AD focuses on learning a representation of normal data samples (clutter) and finding a sphere embracing normal data samples in latent space. However, abnormal samples from artificial objects (underwater targets) have similar physical experiences as normal clutter samples from geological and biological scattering objects. Therefore, it is difficult to discriminate between the target and the clutter using conventional deep AD. To overcome the problem of active sonar classification, we propose semi-supervised learning-based bi-sphere anomaly detection (BiSAD) to find two spheres, embracing target and clutter samples each, by modifying conventional deep AD. Simultaneously, BiSAD searches for the latent space where two sphere centroids locate distantly to promote generalization. In the generalization test, the receiver operating characteristic (ROC) curve of BiSAD indicates a detection probability of 0.8 at a false alarm rate of 0.01, and the area under the ROC curve was 0.989, which was superior to the conventional deep AD and supervised learning-based approaches.

In active sonar systems, detection always suffers from reverberation interference from multiple scatterers in oceanic environments; therefore, numerous studies have been conducted on reverberation suppression. Recently, a non-negative matrix factorization (NMF)-based method was proposed and successfully applied to reverberation suppression. However, the conventional NMF-based method makes convergence challenging because the frequency basis matrix is initialized without considering reverberation characteristic information from oceanic environments. To solve these problems, We propose an improved NMF-based reverberation suppression method adopting a pre-trained reverberation basis matrix and modified sparse update rule. The proposed method is evaluated by analyzing simulation and sea experiment data and the study confirmed that the detection performance was improved compared to the conventional method under various signal-to-reverberation ratio conditions. Several topics are also discussed to analyze the proposed method in detail.

We propose an active sonar target classifier using attention-based complementary learning (ABCL) to mitigate poor generalization with scarce active sonar data. ABCL utilizes the information of different features (spectrograms of short-time Fourier transform and constant-Q transform in the present study), which provide distinct perspectives for the same raw data. The complementary learning module of ABCL first summarizes the input features using a transformer encoder layer, including self-attention. Subsequently, the attention mechanism is applied to the refined input features from the transformer encoder layer to generate a comprehensive feature with better generalization using limited active sonar data. The comprehensive feature from two different features enables a shallow network to discriminate between active targets and nontargets and allows ABCL to be light. Two active sonar datasets from two oceanic environments were used for training and testing. The generalization of ABCL was examined using a receiver operating characteristic curve. ABCL showed a comparable performance to state-of-the-art deep learning (DL) models in vision in a test scenario and achieved the best performance with low variance in the other test scenario, where other DL models showed a poor probability of detection at a low probability of false alarms.